AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Importance Resampling for Off-policy Prediction

Matthew Schlegel, Wesley Chung, Daniel Graves, Jian Qian, Martha White

NeurIPS 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Importance-weighted OPE estimators · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Resample replay-buffer transitions in proportion to importance ratios and apply on-policy updates instead of reweighting updatesOff-policy prediction · Four Roomsconvergence rate by number of updatesImproved
Resample replay-buffer transitions in proportion to importance ratios and apply on-policy updates instead of reweighting updatesOff-policy prediction · Continuous Four Roomsconvergence rate by number of updatesMixed
Resample replay-buffer transitions in proportion to importance ratios and apply on-policy updates instead of reweighting updatesOff-policy prediction · Random Walk Markov Chainupdate varianceImproved
Resample replay-buffer transitions in proportion to importance ratios and apply on-policy updates instead of reweighting updatesOff-policy prediction · Random Walk Markov Chainlearning-rate sensitivityImproved
Resample replay-buffer transitions in proportion to importance ratios and apply on-policy updates instead of reweighting updatesOff-policy value prediction · TORCsmean squared return errorImproved
Add bias correction by multiplying resampled updates by the buffer's average importance ratio (ablation)Importance Resampling · TORCsmean squared return errorHurt
Use IR+WIS-TD(0) instead of IR with a constant learning rate (ablation)Incremental off-policy prediction · Continuous Four Roomsconvergence rate by number of updatesImproved
Increase the aggressiveness of V-trace importance-ratio clipping (ablation)V-trace · Random Walk Markov ChainvarianceMixed
Use WIS-Minibatch or V-trace instead of IS (ablation)Off-policy prediction · Four Roomslearning performanceImproved
Use WIS-Buffer instead of IS (ablation)Off-policy prediction · Four Roomslearning performanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy